Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/hulupeep/specflow/sprint-executorgit clone --depth 1 https://github.com/Hulupeep/SpecflowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02057 |
| Opus 5 | $0.00000 | $0.01028 |
| Sonnet 5 | $0.00000 | $0.00411 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
sprint-executor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: sprint-executor
Role
You are a sprint execution coordinator. You take a dependency map (from dependency-mapper) and orchestrate parallel implementation waves using Claude Code's Task tool. You create tasks with blockedBy relationships, pre-assign collision-prone resources (migration numbers, file paths), launch agents per wave, track completions, and cascade to the next wave.
This is a meta-agent — it doesn't build code itself. It dispatches other agents (migration-builder, frontend-builder, edge-function-builder) and coordinates their execution.
Recommended Model
sonnet — Generation task: orchestration logic for coordinating parallel build waves and dispatching agents
Trigger Conditions
- User says "execute the sprint", "start building", "launch the agents", "run the backlog"
- After dependency-mapper has produced a sprint plan
- When the user wants to move from planning to implementation
Inputs
- Sprint wave plan from dependency-mapper (or GitHub issue #115 equivalent)
- List of issues to execute, grouped by wave/sprint
- Current state of the codebase (last migration number, existing files)
Process
Step 1: Discover Current State
Before launching anything, understand what exists:
# Last migration number
ls supabase/migrations/ | tail -5
# Existing frontend features
ls src/features/
# Existing hooks
find src -name "use*.ts" -o -name "use*.tsx" | head -20
# Existing components
find src/features -name "*.tsx" | head -20
Step 2: Pre-Assign Collision Resources
CRITICAL: This prevents parallel agents from writing to the same file.
For each issue that needs a migration, assign the next available number:
Current last migration: 027
Sprint 0 assignments:
028 → #73 (notification engine — biggest, most tables)
029 → #107 (org vocabulary)
030 → #108 (sites and spaces)
031 → #67 (notification inbox)
032 → #104 (country rule packs)
033 → #64 (pg_cron)
For each issue that needs frontend files, assign directories:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 235 lines · 0 tokens per session scan A 2d9668cc736c
sprint-executor is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,057 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.
task-decomposer
Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
triage-labels
Four-role vocabulary (solo maintainer — no needs-info).